Inferring Contextual User Status and Duration

1. A method comprising: by one or more server computing devices, collecting first data associated with an activity recently performed or currently being performed by a user of one or more client computing devices; by one or more server computing devices, inferring a current state of the user at least in part by analyzing at least the first data; by one or more server computing devices, accessing second data generated from one or more historical durations associated with the inferred current state, the second data comprising data associated with a social graph of a social networking system, the social graph comprising a plurality of nodes and edges connecting the nodes, at least one node in the graph corresponding to the user; and by one or more server computing devices, estimating an end time associated with the inferred current state based at least in part on the second data.

2. The method of claim 1 , wherein: the social-networking system further comprises historical data associated with the user; and the current state of the user is inferred at least in part by analyzing the historical data associated with the user, in addition to the first data.

3. The method of claim 2 , wherein: the historical data comprises information associated with one or more nodes or edges connected to the user's node.

4. The method of claim 1 , further comprising, by one or more server computing devices, providing third data based at least in part on the user's inferred current state and associated estimated end time for presentation to one or more other users, each of the other users having at least one node in the graph corresponding to the other user and connected by one or more edges to at least one of nodes corresponding to the user whose current state was inferred.

5. The method of claim 1 , wherein the first data comprises one or more of: an identifier of one of the one or more client computing devices; an Internet Protocol (IP) address of one of the one or more client computing devices; a location of one of the one or more client computing devices; metadata received from a software application executing on one of the one or more client computing devices; or data received from a radio-frequency identification (RFID) reader attached to one of the one or more client computing devices.

6. The method of claim 1 , wherein analyzing comprises analyzing by use of: regression analysis; decision-tree analysis; neural-network analysis; or expert-system analysis.

7. The method of claim 1 , further comprising, by one or more server computing devices, collecting fourth data comprising feedback from the user regarding the accuracy of the inferred current state.

8. One or more computer-readable non-transitory storage media embodying software that is operable when executed to: collect first data associated with an activity recently performed or currently being performed by a user of one or more client computing devices; infer a current state of the user at least in part by analyzing at least the first data; access second data generated from one or more historical durations associated with the inferred current state, the second data comprising data associated with a social graph of a social networking system, the social graph comprising a plurality of nodes and edges connecting the nodes, at least one node in the graph corresponding to the user; and estimate an end time associated with the inferred current state based at least in part on the second data.

9. The media of claim 8 , wherein: the social-networking system further comprises historical data associated with the user; and the software that is operable when executed to infer a current state of the user comprises software that is operable when executed to infer the current state of the user at least in part by analyzing the historical data associated with the user, in addition to the first data.

10. The media of claim 9 , wherein: the historical data comprises information associated with one or more nodes or edges connected to the user's node.

11. The media of claim 8 , wherein the software is further operable when executed to provide third data based at least in part on the user's inferred current state and associated estimated end time for presentation to one or more other users, each of the other users having at least one node in the graph corresponding to the other user and connected by one or more edges to at least one of nodes corresponding to the user whose current state was inferred.

12. The media of claim 8 , wherein the first data comprises one or more of: an identifier of one of the one or more client computing devices; an Internet Protocol (IP) address of one of the one or more client computing devices; a location of one of the one or more client computing devices; metadata received from a software application executing on one of the one or more client computing devices; or data received from a radio-frequency identification (RFID) reader attached to one of the one or more client computing devices.

13. The media of claim 8 , wherein analyzing comprises analyzing by use of: regression analysis; decision-tree analysis; neural-network analysis; or expert-system analysis.

14. The media of claim 8 , wherein the software is further operable when executed to collect fourth data comprising feedback from the user regarding the accuracy of the inferred current state.

15. A system comprising: one or more processors; and a memory coupled to the processors comprising instructions executable by the processors, the processors being operable when executing the instructions to: collect first data associated with an activity recently performed or currently being performed by a user of one or more client computing devices; infer a current state of the user at least in part by analyzing at least the first data; access second data generated from one or more historical durations associated with the inferred current state, the second data comprising data associated with a social graph of a social networking system, the social graph comprising a plurality of nodes and edges connecting the nodes, at least one node in the graph corresponding to the user; and estimate an end time associated with the inferred current state based at least in part on the second data.

16. The system of claim 15 , wherein: the social-networking system further comprises historical data associated with the user; and the processors that are operable when executing the instructions to infer a current state of the user comprise processors that are operable when executing the instructions to infer the current state of the user at least in part by analyzing the historical data associated with the user, in addition to the first data.

17. The system of claim 16 , wherein: the historical data comprises information associated with one or more nodes or edges connected to the user's node.

18. The system of claim 15 , wherein the processors are further operable when executing the instructions to provide third data based at least in part on the user's inferred current state and associated estimated end time for presentation to one or more other users, each of the other users having at least one node in the graph corresponding to the other user and connected by one or more edges to at least one of nodes corresponding to the user whose current state was inferred.

19. The system of claim 15 , wherein the first data comprises one or more of: an identifier of one of the one or more client computing devices; an Internet Protocol (IP) address of one of the one or more client computing devices; a location of one of the one or more client computing devices; metadata received from a software application executing on one of the one or more client computing devices; or data received from a radio-frequency identification (RFID) reader attached to one of the one or more client computing devices.

20. The system of claim 15 , wherein analyzing comprises analyzing by use of: regression analysis; decision-tree analysis; neural-network analysis; or expert-system analysis.

21. The system of claim 15 , wherein the processors are further operable when executing the instructions to collect fourth data comprising feedback from the user regarding the accuracy of the inferred current state.